espnet2.enh.loss.wrappers.mixit_solver.MixITSolver

source

class espnet2.enh.loss.wrappers.mixit_solver.MixITSolver(criterion: AbsEnhLoss, weight: float = 1.0)

Bases: AbsLossWrapper

Mixture Invariant Training Solver.

• Parameters:
  • criterion (AbsEnhLoss) – an instance of AbsEnhLoss
  • weight (float) – weight (between 0 and 1) of current loss for multi-task learning.

forward(ref: List[Tensor] | List[ComplexTensor], inf: List[Tensor] | List[ComplexTensor], others: Dict = {})

MixIT solver.

• Parameters:
  • ref (List *[*torch.Tensor ]) – [(batch, …), …] x n_spk
  • inf (List *[*torch.Tensor ]) – [(batch, …), …] x n_est
• Returns: (torch.Tensor): minimum loss with the best permutation stats: dict, for collecting training status others: dict, in this PIT solver, permutation order will be returned
• Return type: loss

property name